© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 384
    Prev
    Next
    INDEX
    Explanations

    references to government actions and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "government"

    np_acts-logits-general · gemini-2.0-flash

    government actions and entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parseColor
    -0.49
    usercontent
    -0.48
    лк
    -0.45
    Alpes
    -0.42
     Bote
    -0.42
     ho
    -0.42
    iones
    -0.41
    upar
    -0.41
    EndProject
    -0.41
     الفلك
    -0.41
    POSITIVE LOGITS
     government
    2.41
     Government
    2.20
    Government
    2.03
    government
    2.03
     governments
    1.94
     govt
    1.89
     gouvernement
    1.87
     GOVERNMENT
    1.87
     Govt
    1.79
    GOVERNMENT
    1.74
    Activations Density 0.351%

    No Known Activations